> ## Documentation Index
> Fetch the complete documentation index at: https://docs.stateset.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Your First Workflow Trial

> Connect a helpdesk, draft an automation from existing material, replay tickets in shadow mode, and verify the result before live routing.

<div className="ss-guide-summary" role="group" aria-label="Walkthrough at a glance">
  <div><span className="ss-eyebrow">WORK IN</span><strong>Workflow Studio</strong></div>
  <div><span className="ss-eyebrow">BRING</span><p>Brand access · Gorgias connection · A reviewer</p></div>
  <div><span className="ss-eyebrow">FINISH WITH</span><p>A ticket, its draft, and verified dry-run evidence</p></div>
</div>

**Outcome:** inspect a draft generated for a real helpdesk ticket before allowing the workflow
to send replies. This walkthrough uses Response's setup UI and the Temporal Engine behind it.

Have your organization ready, permission to configure its workflow brand, and Gorgias access.
Connect Shopify too when the workflow needs store policies or commerce context. If you are
still waiting for those credentials, complete [your first agent](/guides/first-support-agent).

## Before you begin

| Verify           | Ready when                                                                          |
| ---------------- | ----------------------------------------------------------------------------------- |
| Brand identity   | You can identify the intended workflow brand UUID                                   |
| Provider access  | An authorized operator can connect Gorgias and any required store context           |
| Routing          | You have checked the actual mode; an existing brand may already handle live traffic |
| Review ownership | Someone can compare a replayed ticket with its draft and policy                     |

**Finish line:** one inspected replay with its ticket ID, run ID, draft, and dry-run evidence.
The accelerator can change configuration and provider setup; review step 2 before starting it.
Record the job ID while it runs so a teammate or assistant can resume inspection without
starting another attempt. Use the [onboarding record](/guides/platform-onboarding#keep-a-record-you-can-resume).

## 1. Select the brand and connect systems

Open [Setup](https://response.stateset.com/setup) and **Connect systems**, or use
[Workflow Studio](https://response.stateset.com/workflow-studio) for an existing brand. Select
the intended brand and connect the providers through the app's connection flow.

Keep the returned workflow brand UUID. Do not substitute the organization ID, store domain, or
brand slug for it in tools that require `brand_id`.

<div className="ss-checkpoint">
  **Success:** the intended providers appear connected and readiness checks identify no unresolved
  credential or configuration blockers. A saved credential alone is not proof of a healthy connection.
</div>

## 2. Draft and run a trial

In **Automate your queue**, choose **Draft & run trial** under
**Draft it from your helpdesk and run a trial**. The accelerator can discover provider IDs,
harvest macros/replies/policies, draft and apply configuration for an inactive brand, register
webhooks, activate an eligible shadow brand, and queue ticket replays.

Inspect each step's report. `ok`, `skipped`, and `failed` mean different things: a finished job
can still contain failed or skipped steps. The process may take several minutes.

<Note>
  The accelerator does not change routing mode. A newly bootstrapped brand starts in `shadow`;
  check the actual mode on an existing brand. The accelerator skips its activation step for
  live/canary brands, and it does not rewrite an already active brand's configuration.
</Note>

If you operate through MCP instead of the UI, use
[the accelerator task](/guides/manage-platform-with-mcp#run-a-workflow-trial) with the same brand.
Do not launch both paths concurrently for the same onboarding attempt.

## 3. Read the first result

Inspect the workflow's runs in Workflow Studio. Through MCP, use `get_trial_report`,
`list_brand_workflows`, and `get_workflow_run` as exposed by your connection.

For one replayed ticket, record:

* The original ticket and workflow run IDs.
* The draft response and the policies/context that support it.
* Any skip, escalation, failure, or review decision.
* Evidence that it was a replay/dry run rather than a customer dispatch.

Backfill runs carry `dry_run: true`, regardless of routing mode. They bypass the human-review
waiting step and send nothing. A successful replay can finish as `dry_run_completed`; seeing
no approval item for it is therefore expected.

<div className="ss-checkpoint">
  **First value:** a reviewer can compare an actual ticket with the draft the workflow would have
  produced and decide what needs improving. “Brand active” or “job queued” alone is not this result.
</div>

## 4. Improve one behavior

Choose a specific gap: missing policy, wrong classification, unnecessary escalation, or an
unhelpful draft. Review the relevant source/configuration and test the change against that case.
Retain human-corrected cases as your evaluation set.

For MCP configuration edits, propose and validate first. Apply against the current config
version with a change note. Unattended configuration changes must use the engine's
`require_golden_pass: true` gate; a missing or failing evaluation is a reason to stop, not lower
the threshold. See [Workstream MCP](/next-temporal/mcp-connector).

## 5. Move to reviewed live traffic

Decide who approves the initial replies and verify the review gate remains enabled. After
reviewing the trial and readiness, an authorized operator can change routing to `canary` or
`live`. Through MCP this is `set_brand_routing_mode`, a separate consequential operation.

Observe a real incoming event, inspect the draft, follow its approval, and verify dispatch.
Only then count a first live outcome. Keep the review gate until your team has evidence for
changing it. Returning routing to `shadow` changes future handling; it does not unsend replies.

## See where onboarding is stuck

Use `get_onboarding_funnel` for the brand's `next_step` and observed timings. The engine tracks
setup milestones separately from real traffic milestones: `first_event_received`, `first_draft`,
and `first_reply_sent` come from actual runs.

| Symptom                               | What to inspect                                                                                          |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------- |
| Discovery/harvest skipped             | Gorgias credentials must be available to the control plane; reconnect through the supported app flow     |
| Activation failed                     | Readiness details, including connector health, configuration, and billing if required                    |
| Draft step skipped on an active brand | Expected; use the explicit draft/review/apply flow for an existing configuration                         |
| Backfill queued but report empty      | Worker/run state, failed runs, and whether replay events actually executed                               |
| No real event received                | Provider webhook registration and brand activation; a successful replay does not verify webhook delivery |
| Drafts appear but replies do not      | Routing mode, review decisions, and dispatch result; shadow/replay drafts are not sent                   |

## Save your progress

Before leaving, update your [onboarding record](/guides/platform-onboarding#keep-a-record-you-can-resume)
with the identifiers, observed result, remaining blocker, and next action. If you switch to an
AI assistant, use the [resume prompt](/guides/platform-onboarding#resume-with-your-ai-assistant)
to verify current state before continuing.

## Next steps

<CardGroup cols={2}>
  <Card title="Improve one behavior" icon="git-pull-request" href="/guides/first-workflow-config-change">
    Propose, evaluate, apply, and verify a versioned configuration change.
  </Card>

  <Card title="Review your first week" icon="chart-line" href="/guides/first-week-with-stateset">
    Plan reviewed live outcomes and measure what improves.
  </Card>
</CardGroup>

Related: [Troubleshoot onboarding](/guides/onboarding-troubleshooting) · [Manage agents and workflows with MCP](/guides/manage-platform-with-mcp) · [Durable workflow API walkthrough](/guides/temporal-first-durable-workflow) · [From signup to first value](/guides/platform-onboarding).